{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3VN7YMEYKDLJJTNO6EVCICDSD5","short_pith_number":"pith:3VN7YMEY","schema_version":"1.0","canonical_sha256":"dd5bfc309850d694cdaef12a2408721f5743ddaecbf3fbb8a55e19f4bc0fe27e","source":{"kind":"arxiv","id":"2504.04840","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Fanman Meng, Heqian Qiu, Hongliang Li, Lanxiao Wang, Qingbo Wu, Zhaofeng Shi","submitted_at":"2025-04-07T08:51:11Z","abstract_excerpt":"Even from an early age, humans naturally adapt between exocentric (Exo) and egocentric (Ego) perspectives to understand daily procedural activities. Inspired by this cognitive ability, we propose a novel Unsupervised Ego-Exo Dense Procedural Activity Captioning (UE$^{2}$DPAC) task, which aims to transfer knowledge from the labeled source view to predict the time segments and descriptions of action sequences for the target view without annotations. Despite previous works endeavoring to address the fully-supervised single-view or cross-view dense video captioning, they lapse in the proposed task"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.04840","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-07T08:51:11Z","cross_cats_sorted":[],"title_canon_sha256":"91275803fb23cc157d165f47860ea2b2fcbb8493f0ce5ae990dcba1ee78d602f","abstract_canon_sha256":"e99985fde3610196a10503754308b8a0de8d39908a36e09f06a18b9d7f3386b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:30.401172Z","signature_b64":"aT8PlykocuWBSfUT0rNAVB2tQRz2W4Mm4jdZKMT6t187CmcYJHFnRbBB3xPcPfD42z6xlu5b49YqS22kC99ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd5bfc309850d694cdaef12a2408721f5743ddaecbf3fbb8a55e19f4bc0fe27e","last_reissued_at":"2026-07-05T11:36:30.400732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:30.400732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Fanman Meng, Heqian Qiu, Hongliang Li, Lanxiao Wang, Qingbo Wu, Zhaofeng Shi","submitted_at":"2025-04-07T08:51:11Z","abstract_excerpt":"Even from an early age, humans naturally adapt between exocentric (Exo) and egocentric (Ego) perspectives to understand daily procedural activities. Inspired by this cognitive ability, we propose a novel Unsupervised Ego-Exo Dense Procedural Activity Captioning (UE$^{2}$DPAC) task, which aims to transfer knowledge from the labeled source view to predict the time segments and descriptions of action sequences for the target view without annotations. Despite previous works endeavoring to address the fully-supervised single-view or cross-view dense video captioning, they lapse in the proposed task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04840","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.04840/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.04840","created_at":"2026-07-05T11:36:30.400792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04840v3","created_at":"2026-07-05T11:36:30.400792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04840","created_at":"2026-07-05T11:36:30.400792+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VN7YMEYKDLJ","created_at":"2026-07-05T11:36:30.400792+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VN7YMEYKDLJJTNO","created_at":"2026-07-05T11:36:30.400792+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VN7YMEY","created_at":"2026-07-05T11:36:30.400792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VN7YMEYKDLJJTNO6EVCICDSD5","json":"https://pith.science/pith/3VN7YMEYKDLJJTNO6EVCICDSD5.json","graph_json":"https://pith.science/api/pith-number/3VN7YMEYKDLJJTNO6EVCICDSD5/graph.json","events_json":"https://pith.science/api/pith-number/3VN7YMEYKDLJJTNO6EVCICDSD5/events.json","paper":"https://pith.science/paper/3VN7YMEY"},"agent_actions":{"view_html":"https://pith.science/pith/3VN7YMEYKDLJJTNO6EVCICDSD5","download_json":"https://pith.science/pith/3VN7YMEYKDLJJTNO6EVCICDSD5.json","view_paper":"https://pith.science/paper/3VN7YMEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04840&json=true","fetch_graph":"https://pith.science/api/pith-number/3VN7YMEYKDLJJTNO6EVCICDSD5/graph.json","fetch_events":"https://pith.science/api/pith-number/3VN7YMEYKDLJJTNO6EVCICDSD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VN7YMEYKDLJJTNO6EVCICDSD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VN7YMEYKDLJJTNO6EVCICDSD5/action/storage_attestation","attest_author":"https://pith.science/pith/3VN7YMEYKDLJJTNO6EVCICDSD5/action/author_attestation","sign_citation":"https://pith.science/pith/3VN7YMEYKDLJJTNO6EVCICDSD5/action/citation_signature","submit_replication":"https://pith.science/pith/3VN7YMEYKDLJJTNO6EVCICDSD5/action/replication_record"}},"created_at":"2026-07-05T11:36:30.400792+00:00","updated_at":"2026-07-05T11:36:30.400792+00:00"}